JP2023064174A - Data processor, data processing method, and production system - Google Patents

Abstract

To provide a data processor, a data processing method, and a production system capable of obtaining an optimum set value of a final control element upon brand change.SOLUTION: A data processor 20 includes: a collection part 21 which collects set values of a final control element for controlling a product production process in a predefined cycle and also collects brand information indicating brands of products; a first processing part 22a which performs statistical processing on the set values of the final control element collected by the collection part 21 to obtain, as an actual operation value, a representative value of the set values of the final control element during product production and generates an actual value database DB including an actual operations value linked with the brand information; a second processing part 22b which performs statistical processing on the actual operation value linked with the brand information indicating the next brand out of the actual operation values included in the actual value database DB to obtain an optimum set value of the final control element for producing products of the next brand; and an output part 24 which outputs the set value obtained at the second processing part 22b.SELECTED DRAWING: Figure 1

Description

The present invention relates to a data processing device, a data processing method, and a production system.

In a plant where products are produced by continuous production, when different brands (variety) of products are continuously produced by changing the input amount of raw materials, raw material composition, operating conditions, etc. There is Here, continuous production refers to a production method in which raw materials are continuously fed and the manufactured products are continuously taken out. Such plants include, for example, chemical plants and paper plants.

The following Patent Documents 1 and 2 disclose inventions in which the set value of the saturated vapor pressure for drying in the dryer of the papermaking process is obtained by simulation calculation using a physical model of dryer drying based on heat balance in a paper manufacturing plant. there is In the inventions disclosed in Patent Documents 1 and 2, when the brand of paper to be produced is changed (at the time of paper grade change), the set value of the saturated vapor pressure of the dryer is set based on the heat balance based on the basis weight of the brand and the production speed. is expected.

Japanese Patent No. 3094798 Japanese Patent No. 4162864

By the way, if a brand change is performed during continuous production, the product in the transition period of the brand change is discarded as a loss or collected and reused as a raw material. In order to reduce such products, it is necessary to find the optimum setting values for each final operating end for the next brand and shorten the transition period. However, in the methods disclosed in the above-mentioned Patent Documents 1 and 2 (methods for determining the set value of the operation terminal by simulation calculation using a physical model), due to the influence of factors that could not be assumed in the physical model, etc., There is a problem that it is sometimes difficult to find the optimum set value.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a data processing apparatus, a data processing method, and a production system capable of finding the optimum set value of the operating terminal when changing brands.

In order to solve the above problems, a data processing device (20) according to one aspect of the present invention collects set values for an operation terminal that controls a production process of a product at a predetermined cycle, and indicates the brand of the product. a collecting unit (21) for collecting brand information; and performing statistical processing on the setting values of the operation terminal collected by the collecting unit, and calculating the time period during which the product of the brand indicated by the brand information is being produced. a first processing unit (22a) for obtaining a representative value of the set values of the operating terminal as actual operation values and generating an actual value database (DB) containing the actual operation values linked with the brand information; Statistical processing is performed on the actual operation values linked with brand information indicating the next brand to be produced in the production process among the actual operation values contained in the value database to determine the product of the next brand. It comprises a second processing section (22b) for obtaining the optimum setting values of the operation terminal for production, and an output section (24) for outputting the setting values obtained by the second processing section.

Further, in the data processing device according to one aspect of the present invention, the statistical processing performed by the first processing unit is processing for obtaining an average value or a median value of the set values of the operating terminals collected by the collecting unit. .

Further, in the data processing device according to the aspect of the present invention, the first processing unit stably produces the product of the brand indicated by the brand information among the setting values of the operation terminal collected by the collecting unit. The statistical processing is performed on the set values obtained when the

Further, in the data processing device according to the aspect of the present invention, before the first processing unit performs the statistical processing, among the setting values of the operation terminal collected by the collecting unit, the set values are out of a predetermined range. are excluded.

Further, in the data processing device according to one aspect of the present invention, the statistical processing performed by the second processing unit is based on the actual operation value linked with brand information indicating the next brand to be produced in the production process. It is a process of obtaining an average value or a median value or a weighted statistical process.

Further, in the data processing device according to an aspect of the present invention, the second processing unit, before performing the statistical processing, stores the operation record linked with brand information indicating the next brand to be produced in the production process. A process of excluding values outside a predetermined range is performed.

A data processing method according to one aspect of the present invention includes a collection step (S11) of collecting setting values of an operation terminal that controls a production process of a product at a predetermined cycle, and collecting brand information indicating the brand of the product. and performing statistical processing on the set values of the operation terminal collected in the collecting step to obtain a representative value of the set values of the operation terminal during production of the product of the brand indicated by the brand information. A first processing step (S15, S16) of generating a performance value database (DB) containing the operation performance values obtained as performance values and linked to the brand information (S15, S16); and the operation performance values contained in the performance value database. Statistical processing is performed on the actual operation value associated with the brand information indicating the next brand to be produced in the production process, and the optimization of the operation terminal for producing the product of the next brand. and an output step (S24) for outputting the set value obtained in the second processing step.

A production system (1) according to one aspect of the present invention includes a data processing device (20) according to any one of the above, and a setting value output from the data processing device, which is displayed as a recommended value on a display section (11). or a production control system (10) that controls the production of products by setting the set values output from the data processing device to the operation terminals.

Further, a production system according to one aspect of the present invention is a system for controlling a paper machine (40) for producing paper as the product, wherein the data processing device controls at least the paper machine as a set value of the operation terminal. The degree of opening of the seed port valve (B5) for supplying the pulp raw material and the saturated vapor pressure for drying in the dryers (46a, 46b) provided in the paper machine are collected.

According to the present invention, there is an effect that the optimum setting value of the operating terminal can be obtained when the brand is changed.

1 is a block diagram showing the essential configuration of a production system according to one embodiment of the present invention; FIG. 1 is a diagram showing part of the production process of paper produced by a production system according to one embodiment of the present invention; FIG. It is a figure which shows an example of the performance value database in one Embodiment of this invention. 4 is a flowchart showing database generation processing performed by the data processing device according to one embodiment of the present invention; It is a figure which shows an example of the setting value collected by the data processor in one Embodiment of this invention. 4 is a flowchart showing optimum setting value calculation processing performed by the data processing device according to the embodiment of the present invention; It is a figure which shows an example of the operation performance value processed with the data processor in one Embodiment of this invention. It is an example of a display of the optimal set value in one embodiment of the present invention.

Hereinafter, a data processing device, a data processing method, and a production system according to embodiments of the present invention will be described in detail with reference to the drawings. In the following, first, an outline of this embodiment will be described, and then details of each embodiment will be described.

〔overview〕
The embodiment of the present invention enables the optimum set value of the operating terminal to be obtained when the brand is changed. Generally, when a brand is changed, feedforward control is performed on each operation end so that the product quality reaches the quality of the brand after the change as soon as possible. In order to perform such feedforward control, it is necessary to obtain optimum set values for each control element. The embodiment of the present invention enables to find the optimum set values for each of these operating ends.

Conventionally, for example, the set value of the saturated vapor pressure for drying in the dryer in the papermaking process has been obtained by simulation calculation using a physical model of dryer drying based on the heat balance as described in Patent Documents 1 and 2 described above. In order to accurately determine the vapor pressure necessary for drying moisture from paper by calculation using such a physical model, it is necessary to accurately set parameters such as the heat transfer coefficient and specific heat of each layer involved in heat transfer, and The drying efficiency due to water evaporation and the amount of water brought into the dryer must be modeled accurately.

However, it is strictly impossible to perfectly model all these physical phenomena. Even if the physical phenomena described above can be modeled, the parameters used in the model calculations will change depending on environmental conditions such as ambient temperature and humidity, as well as the mix of paper materials. extremely difficult to do. For this reason, methods using these physical models cannot fully respond to long-term changes in production equipment or the addition of new brands, even if each parameter is tuned once. It was difficult to obtain a suitable set value.

In the embodiment of the present invention, instead of predicting the set value of the final control by physical calculation (white-box model) as in the prior art, the prediction of the set value of the final final end based on a statistical method and past performance data ( By performing a black box model), we are always trying to find the optimum setting value. Specifically, even if there are disturbance factors that cannot be grasped, or if the optimum set values change due to gradual changes in equipment and processes, the optimum set values for each control element that take these factors into consideration should be obtained. I have to.

In the embodiment of the present invention, first, set values for the operation end that controls the production process of the product are collected at a predetermined cycle, and brand information indicating the brand of the product is collected. Next, statistical processing is performed on the collected setting values of the operating elements, and a representative value of the setting values of the operating elements during production of the product of the brand indicated by the brand information is obtained as an actual operation value, Generate a performance value database containing operation performance values linked to brand information. Then, among the actual operation values contained in the actual value database, statistical processing is performed on the actual operation values linked with the brand information indicating the next brand to be produced in the production process, and the next brand product is produced. Find and output the optimum set value of the final control element for As a result, it is possible to obtain the optimum setting value of the operating terminal when changing the brand.

〔detail〕
<Production system>
FIG. 1 is a block diagram showing the essential configuration of a production system according to one embodiment of the present invention. As shown in FIG. 1, the production system 1 of this embodiment includes a production control system 10 and a data processing device 20, and produces a predetermined product through continuous production. Examples of products produced by the production system 1 through continuous production include paper and petrochemical products. In this embodiment, for ease of understanding, it is assumed that the product continuously produced by the production system 1 is paper.

FIG. 2 is a diagram showing part of the production process of paper produced by the production system according to one embodiment of the present invention. As shown in FIG. 2, the paper production process includes a preparation process PR1 and a papermaking process PR2. Preparation process PR1 is a process of preparing the raw material used by papermaking process PR2. In this process, fillers, dyes, chemicals, etc. are adjusted and blended with pulp raw materials. The paper making process PR2 is a process for performing so-called papermaking. In this step, the raw material prepared in the preparation step PR1 is supplied to a paper machine 40 for making paper.

A preparation device 30 used in the preparation step PR1 includes a raw material tank 31, a filler tank 32, dye tanks 33a to 33c, chemical tanks 34a and 34b, a mixing chest 35, and a machine chest . The pulp raw material stored in the raw material tank 31, the filler stored in the filler tank 32, the dyes stored in the dye tanks 33a to 33c, and the chemicals stored in the chemical tanks 34a and 34b can be supplied to the mixing chest 35. It is configured.

Specifically, the pulp raw material stored in the raw material tank 31 is supplied to the mixing chest 35 by opening the operation valve B1. The filler stored in the filler tank 32 is supplied to the mixing chest 35 by opening the operation valve B2. The dyes stored in the dye tanks 33a-33c are supplied to the mixing chest 35 by opening the operation valves B3a-B3c. The chemicals stored in the chemical tanks 34a and 34b are supplied to the mixing chest 35 by opening the operation valves B4a and B4b.

The pulp raw material supplied from the raw material tank 31, the filler supplied from the filler tank 32, the dyes supplied from the dye tanks 33a to 33c, and the chemicals supplied from the chemical tanks 34a and 34b are mixed in the mixing chest 35. The mixture mixed in the mixing chest 35 is supplied to the seed box 41 of the papermaking process PR2 after papermaking chemicals such as sticky agents are added in the machine chest 36 .

The paper machine 40 used in the papermaking process PR2 includes a seed box 41, a head box 42, a forming device 43, a dewatering device 44, a white water pit 45, a pre-dryer 46a, an after-dryer 46b, a quality measuring device 47, and a winding device 48. . The seed box 41 is a container in which the raw material supplied from the preparation process PR1 is stored while adjusting the concentration thereof and flowed down at a constant pressure. The raw material stored in the seed box 41 is supplied to the head box 42 by opening the seed port valve B5.

The head box 42 rectifies the raw material supplied from the seed box 41 through the seed port valve B5 into a predetermined width and thickness, and jets it toward the molding device 43 at a predetermined speed. The forming device 43 forms a paper layer by placing the raw material ejected from the head box 42 on a wire, dehydrating and filtering the raw material. This molding device 43 is a device that controls a so-called wire part. The dewatering device 44 mechanically compresses and dehydrates the paper layer formed by the forming device 43, and reduces wire marks and the like to improve paper quality. This dewatering device 44 is a device that controls a so-called press part. The white water pit 45 is a storage tank in which water (white water) squeezed out by the molding device 43 and the dewatering device 44 is collected.

The pre-dryer 46a and the after-dryer 46b dry the paper layer supplied from the dehydrator 44 to reduce the moisture contained in the paper layer to a predetermined moisture content. The pre-dryer 46a and the after-dryer 46b are of generally similar construction and comprise a plurality of steam drums heated by the introduction of steam therein. The paper layer supplied from the dehydrator 44 is dried by being sequentially wound around a plurality of steam drums provided in the pre-dryer 46a and the after-dryer 46b.

The quality measuring device 47 online measures the quality of the paper (paper as a product) supplied from the after-dryer 46b. Note that online measurement means to sequentially measure the quality of produced paper without stopping paper production. The quality measuring device 47 includes a grammage meter, a moisture meter, a paper thickness meter, an ash meter, a spectrophotometer, etc. using radiation (for example, X-rays and β rays) or infrared rays. The grammage [g/m ² ], moisture content [%], thickness [μm], gray content [%], hue (for example, hue in the CIELAB color space), etc. of the supplied paper are measured online. The winding device 48 is a device that winds the paper that has passed through the quality measuring device 47 into a roll.

The production control system 10 controls the production of paper as a product by controlling the preparation device 30 and the paper machine 40 shown in FIG. The production control system 10 is, for example, a distributed control system (DCS) in which controllers for controlling field devices (measuring devices, operating devices) called field devices are distributed for each of several control loops. can be used.

The production control system 10 controls the production of paper as a product by adjusting the set values of the operation elements that control the paper production process including the preparation process PR1 and the papermaking process PR2 shown in FIG. Here, for example, the operation valves B2, B3a to B3c, B4a, and B4b can be mentioned as the operation end in the preparation process PR1 shown in FIG. The amount of filler (ash content) added to the raw material is adjusted by the set value of the operation valve B2, the amount of dye added to the raw material is adjusted by the set values of the operation valves B3a to B3c, and the set values of the operation valves B4a and B4b. adjusts the amount of chemicals added to the raw material.

Further, the operation points in the papermaking process PR2 shown in FIG. 2 include, for example, the seed port valve B5, the slice opening in the head box 42, and the saturated vapor pressure for drying in the pre-dryer 46a and the after-dryer 46b. The amount of material supplied to the paper machine 40 is adjusted by the set value of the seed port valve B5, and the amount of material ejected from the head box 42 to the molding device 43 is adjusted by the set value of the slice opening. Moreover, the temperature of a plurality of steam drums provided in the pre-dryer 46a and the after-dryer 46b is adjusted by the saturated steam pressure for drying.

The production control system 10 refers to the current state of the paper production process, and adjusts the set values of the above-described operating elements. Here, the current state of the paper production process includes the measurement results of the quality measuring device 47 shown in FIG. and various measured values (temperature, pressure, liquid level, etc.) other than the measurement result of the quality measuring device 47 .

The production control system 10 outputs brand information indicating the brand of paper currently being produced to the data processor 20 . The production control system 10 outputs brand information indicating the next brand to be produced in the production process when the brand is changed during continuous production. Further, when a set value is output from the data processing device 20 when a brand change is implemented, the production control system 10 displays the set value on the display unit 11 as a recommended value, or displays the set value is set as the operating end to control paper production.

<Data processor>
The reason why the set values output from the data processor 20 are displayed on the display unit 11 of the production control system 10 is that the optimum set values for the operating terminal at the time of brand change are presented as recommended values to the operator of the production plant. It is for The reason why the set value output from the data processor 20 is set to the operation terminal and the paper production is controlled is that when the brand is changed, automatic control using the optimum set value is realized, and during the transition period of the brand change. to be as short as possible.

The data processing device 20 includes a collection unit 21, a data processing unit 22, a storage unit 23, and an output unit 24. Using various information obtained from the production control system 10, the data processing unit 20 optimizes the operating terminal when the brand is changed. Get the setting value. The data processing device 20 is connected to the production control system 10 via a network, for example, so as to be able to communicate with the production control system 10, collects the above various information via the network, and determines the optimum set values via the network. output to the production control system 10. Note that the network may be a wired network or a wireless network.

The collecting unit 21 collects the setting values of the above-described operating devices from the production control system 10 at a predetermined cycle (for example, one-second cycle or one-minute cycle), and indicates the brand of paper currently being produced. Collect stock information. The collection unit 21 also collects brand information indicating the next brand output from the production control system 10 when the brand is changed. In addition, the collection unit 21 may collect process data (data on temperature, pressure, liquid level, etc.) obtained in the paper production process. The cycle of collecting the process data may be the same as or different from the cycle of collecting the setting values of the operating device described above.

The data processing unit 22 includes a first processing unit 22a and a second processing unit 22b. The data processing unit 22 uses the setting values and brand information of the operating unit collected by the collecting unit 21 to optimize the operating unit when the brand is changed. setting value. The first processing unit 22a performs statistical processing on the setting values of the operation terminal collected by the collection unit 21, and represents the setting values of the operation terminal during production of paper of the brand indicated by the brand information. Calculate the value as the actual operation value. Then, the first processing unit 22a generates a performance value database DB including operation performance values linked with the brand information.

FIG. 3 is a diagram showing an example of a performance value database in one embodiment of the present invention. In the performance value database DB illustrated in FIG. 3, "time", "brand", and "operation performance value" are linked. "Time" indicates the time when the product was produced. As this time, for example, the time when production of the product is started can be used. "Brand" indicates the brand of the product (paper). "Actual operation value" is a representative value of set values in a plurality of operation terminals.

For example, the first row of the performance value database DB illustrated in FIG. SV11, SV12 and SV13. The second line indicates that at time t2, paper of the brand "Paper B" is produced, and the operation performance values of the three control elements specified in advance at that time are SV21, SV22, and SV23. ing. The three predetermined operating ends are, for example, the saturated vapor pressure for drying in the seed port valve B5, the pre-dryer 46a and the after-dryer 46b in the papermaking process PR2 shown in FIG.

Here, the statistical processing performed by the first processing unit 22a is, for example, processing for obtaining the average value or the median value of the set values of the operating terminals collected by the collection unit 21. FIG. The first processing unit 22a compares the setting values obtained when the product (paper) of the brand indicated by the brand information is being stably produced among the setting values of the operation terminal collected by the collecting unit 21. statistical processing. This is higher than the representative value obtained using the set values obtained when paper as a product is not stably produced. This is because it is desirable to use the obtained representative value as the actual operation value.

For example, at least one of the following determination methods can be used as a method for determining whether or not paper as a product is stably produced.
- Determination based on the measurement results of the quality measuring device 47 (see FIG. 2) being within the target range - Measurement results of the quality measuring device 47 or other measuring devices (including online measuring devices or offline measuring devices not shown) ) based on the determination that a product flag (non-defective product flag) is set to indicate that a product of a certain quality or higher is being produced. Judgment based on the fact that the flag indicating that there is

Further, the first processing unit 22a performs a process of excluding setting values of the operation terminal collected by the collection unit 21 that are outside a predetermined range before performing the above statistical processing. This is to exclude set values that are significantly different during the transition period of the brand change as outliers. As a method of excluding outliers, for example, the quartile method can be used.

The second processing unit 22b performs statistical processing on the operation performance values linked with the brand information indicating the next brand to be produced in the production process among the operation performance values contained in the performance value database DB, Optimal setting values of the final control element for producing the next brand of product are obtained. For example, when the next brand to be produced in the production process is "Paper A", the second processing unit 22b performs the first and fourth rows of the performance value database DB illustrated in FIG. Statistical processing is performed on the actual values to find the optimum setting values of the final end for producing "Paper A".

The second processing unit 22b performs the above statistical processing for each operating terminal. For example, the actual operation values SV11 and SV41 in the first and fourth rows of the actual value database DB illustrated in FIG. 3 are those of the seed port valve B5 shown in FIG. 2, and the actual operation values SV13 and SV43 are the saturated vapor pressure for drying in the after-dryer 46b shown in FIG. The second processing unit 22b individually performs statistical calculations for the actual operation values SV11 and SV41, statistical calculations for the actual operational values SV12 and SV42, and statistical calculations for the actual operational values SV13 and SV43.

Here, the statistical processing performed by the second processing unit 22b is, for example, processing for obtaining the average value or median value of the actual operation values or weighted statistical processing for the actual operation values (for example, processing for obtaining a weighted moving average, using a Kalman filter processing, etc.). The second processing unit 22b may perform statistical processing after weighting the operation performance values (for example, weighting such that the newer the operation performance values are weighted more heavily). Before performing the above statistical processing, the second processing unit 22b excludes values outside a predetermined range from the actual operation values linked with the brand information indicating the next brand to be produced in the production process. process. This is to obtain a more optimal setting value by excluding setting values that are greatly different from each other as outliers. As a method of excluding outliers, for example, the quartile method can be used.

The storage unit 23 stores the performance value database DB generated by the first processing unit 22a of the data processing unit 22. FIG. As the storage unit 23, for example, a volatile semiconductor memory such as a RAM (Random Access Memory) or a non-volatile semiconductor memory such as a flash memory can be used. In addition, the storage unit 23 is not limited to a semiconductor memory, and a HDD (Hard Disk Drive), SSD (Solid State Drive), or the like can be used in addition to the semiconductor memory. The output unit 24 outputs the optimum set values obtained by the second processing unit 22b of the data processing unit 22 to the production control system 10. FIG.

<Data processing method>
Next, operation of the data processing device 20 according to one embodiment of the present invention will be described. The operation of the data processing device 20 includes a process of collecting set values of the operation terminals that control the paper production process and generating an actual value database DB (hereinafter referred to as "database generation process"), and using the actual value database DB. and the process of obtaining the optimum setting value of the operating terminal at the time of brand change (hereinafter referred to as "optimum setting value calculation process"). The details of these processes will be described in order below.

《Database generation process》
FIG. 4 is a flowchart showing database generation processing performed by the data processing device according to one embodiment of the present invention. The processing of the flowchart shown in FIG. 4 is started each time the brand is changed in the paper production process. When the process is started, first, the collection unit 21 collects the setting values of the operation terminal from when the brand is changed until when the next brand is changed (step S11: collection step).

Specifically, during the period from when the brand is changed until when the next brand is changed, the set values of the plurality of operating terminals are changed at a predetermined cycle (for example, one-second cycle or one-minute cycle). Processing to collect is performed. The plurality of operation terminals from which the set values are collected include, for example, the seed port valve B5 shown in FIG. The collected setting values are recorded together with brand information indicating the brand of paper currently being produced.

FIG. 5 is a diagram showing an example of setting values collected by the data processing device according to one embodiment of the present invention. In the graph shown in FIG. 5, the horizontal axis represents time and the vertical axis represents set values. The horizontal axis of the graph shown in FIG. 5 is based on the time when the brand was changed, and the time shown on the horizontal axis represents the elapsed time from the time when the brand was changed. It should be noted that FIG. 5 shows only the set value of one of the set values of a plurality of manipulators. The setting values shown in FIG. 5 change greatly until about 100 seconds have elapsed immediately after the brand change, and after that the values generally fall within a certain value (the setting values become stable). show.

Next, the first processing unit 22a performs a process of extracting setting values for a certain period of time from the setting values of the operation terminals collected by the collecting unit 21 (step S12). For example, there is a process of extracting the set values from among the set values of the operation terminals collected by the collection unit 21 until a predetermined time (for example, about several tens of minutes) has passed since the brand was changed. done. This processing is performed to limit the number of set values used in the statistical processing performed by the first processing section 22a to obtain the actual operation value. For example, in the example shown in FIG. 5, the setting values are extracted until approximately 1200 seconds (20 minutes) have passed since the brand change was performed.

Next, a process of excluding outliers from the extracted setting values is performed by the first processing unit 22a (step S13). Specifically, a process of excluding setting values outside a predetermined range is performed. For example, a process of excluding setting values outside the range (predetermined range) W defined by the lower limit threshold TH1 and the upper limit threshold TH2 shown in FIG. 5 is performed. Note that the lower threshold value TH1 and the upper threshold value TH2 are, for example, calculated in advance using the values of the first quartile, the third quartile, and the interquartile range obtained by the quartile method from the extracted setting value. It may be set by a specified calculation (processing) method, or may be set in advance for each paper brand. When setting in advance for each paper brand, for example, it can be determined based on past set values obtained for each paper brand.

Subsequently, the first processing unit 22a performs a process of removing the set values of the portion where the product is not stably produced (step S14). For example, processing is performed to remove the set value obtained when the measurement result of the quality measuring device 47 (see FIG. 2) is not within the target range. In the example shown in FIG. 5, the set value in the period T1 from when the brand is changed until the measurement result of the quality measuring device 47 first enters the target range is removed. By performing this process, the set values obtained when paper is stably produced remain.

Subsequently, the first processing unit 22a performs statistical processing on the set values that have undergone the above processing, and calculates an operation performance value that is a representative value of the set values (step S15: first processing step). For example, the first processing unit 22a calculates the average value or the median value of the set values for which the above processing is performed as the actual operation value V1 shown in FIG. In addition, the first processing unit 22a calculates the actual operation value for each of the plurality of operation terminals for which the set values are collected.

After the above process is completed, the first processing unit 22a performs a process of generating a performance value database DB including operation performance values linked with brand information (step S16: first processing step). Specifically, the brand information indicating the brand of paper produced while the set values were being collected is linked to each of the actual operation values calculated in step S15 to generate the actual value database DB. processing takes place. Incidentally, like the actual value database DB illustrated in FIG. 3, in addition to the brand information, the time information indicating the time when the product was produced may be associated with the actual operation value. The generated actual value database DB is stored in the storage unit 23 . Through the above process, the actual value database DB is generated.

<<Optimum set value calculation process>>
FIG. 6 is a flowchart showing optimum setting value calculation processing performed by the data processing device according to one embodiment of the present invention. The processing of the flowchart shown in FIG. 6 is started each time the brand is changed in the paper production process. When the brand is changed, brand information indicating the next brand is output from the production control system 10 and collected by the collection unit 21 of the data processing device 20 .

When the process is started, first, the process of acquiring the operation performance value obtained by linking the same brand information as the brand information (brand information indicating the next brand) collected by the collection unit 21 from the actual value database DB is performed first. 2 processing section 22b (step S21). For example, when the brand information indicating the next brand collected by the collecting unit 21 is “Paper A”, the second processing unit 22b collects Get the actual operation value of the line.

Next, the second processing unit 22b performs a process of excluding outliers from the acquired operational performance values (step S22). In this process, for example, similar to the process of step S13 shown in FIG. 4, the range defined by the lower limit threshold and the upper limit threshold (similar to the range W defined by the lower limit threshold TH1 and the upper limit threshold TH2 shown in FIG. range) are excluded.

FIG. 7 is a diagram showing an example of actual operation values processed by the data processing device in one embodiment of the present invention. In the graph shown in FIG. 7, the horizontal axis represents time and the vertical axis represents actual operation values. 7, similarly to FIG. 5, only the actual operation value of one of the actual operation values of a plurality of operation terminals is shown. By performing the process of step S22, as shown in FIG. 7, the actual operation values (actual operation values excluding outliers) when the same brand as the next brand was produced in the past are arranged in chronological order. You get what you get.

Subsequently, the second processing section 22b performs statistical processing on the actual operation values for which the above processing has been performed, and obtains the optimum setting values of the operation end for producing the next brand of paper. (Step S23: second processing step). For example, the second processing unit 22b, among the actual operation values for which the above processing has been performed, the average value or A process of obtaining the median value or a weighted statistical process (for example, a process of obtaining a weighted moving average, a process using a Kalman filter, etc.) is calculated as the optimum setting value of the control terminal. In addition, the second processing unit 22b calculates the optimum set value for each of the plurality of operation terminals for which the operation performance values are collected.

When the above process is finished, the output unit 24 performs a process of outputting the calculated optimum setting value of the operating terminal (step S24: output step). The optimum set values for the operation terminal output from the output unit 24 are input to the production control system 10 and displayed as recommended values on the display unit 11, or set to the operation terminal to produce the next brand of paper. Through the above processing, the optimum setting values for each of the plurality of operation terminals are calculated and used in the production control system 10. FIG.

FIG. 8 is a display example of optimum setting values in one embodiment of the present invention. In the example shown in FIG. 8, among the plurality of operation ends in the production plant, the opening of the seed valve B5 (seed valve opening), the saturated vapor pressure for drying in the pre-dryer 46a (pre-vapor pressure), and the after-dryer 46b Only the set value of the saturated vapor pressure for drying (after vapor pressure) is illustrated. In the example shown in FIG. 8, the display unit 11 of the production control system 10 displays the set value (start) at the start of production and the current set value (current) at each operation terminal. In addition to the setting values for each of the operation terminals, the optimum setting values for each operation terminal are displayed as "recommended values".

In this manner, the display unit 11 of the production control system 10 displays, as a recommended value, the optimal setting values of the operation terminal for producing the product of the next brand when the brand is changed. Therefore, an operator (operator) of the production plant can shorten the transition period for brand change by changing the setting value to the displayed recommended value if necessary. This reduces the amount of products produced during the transition period (products that are discarded as losses or recovered and reused as raw materials). Incidentally, a prediction based on a conventional physical model may also be performed in parallel, and may be displayed in parallel with the recommended values in the display unit 11 so that the operator can select which one to use.

As described above, in the present embodiment, statistical processing is performed on the set values of the operating device collected at a predetermined cycle to obtain the actual operation value, and the actual operation value including the actual operation value linked to the brand information is obtained. Generate a value database DB. Statistical processing is performed on the actual operation values linked with the brand information indicating the next brand among the actual operation values included in the actual value database DB, and the operating terminal for producing the product of the next brand is selected. Optimal setting values are obtained and output. As a result, it is possible to obtain the optimum set value of the operating terminal when changing the brand, without depending on the accuracy of the physical model and always reflecting the latest operating conditions.

In addition, in the present embodiment, a representative value of the set values set to the operating terminals when producing a certain brand of product is stored in the actual value database DB as the actual operation value. Then, when the product of the brand is produced again, the operation performance values obtained when the product of the brand was produced in the past are read from the performance value database DB and used to calculate the optimum set value. . As a result, there is no need to manually record the set values of the control elements that have been set in the past, thereby reducing the burden on the operator (operator) of the production plant and preventing erroneous recording.

Although the data processing device, data processing method, and production system according to one embodiment of the present invention have been described above, the present invention is not limited to the above-described embodiments and can be freely modified within the scope of the present invention. is. For example, in the above-described embodiment, the first processing unit 22a of the data processing device 20 calculates the average value or the median value of the set values obtained when paper is stably produced as the actual operation value. . However, the first processing unit 22a may use a set value obtained when a product flag (a flag indicating that a product of a certain quality or higher is being produced) is set for the first time as the actual operation value.

Also, before the first processing unit 22a of the data processing device 20 calculates the actual operation value, the set value used for calculating the actual operation value may be corrected using information other than the set value. Examples of setting value correction include the following.
・When the product produced during the transition period of the brand change is reused as a raw material, the filler addition rate is corrected according to the addition rate of the reused product ・Seed valve B5 (Fig. 2 ) ・Correction of the opening of the seed port valve B5 according to the seed concentration ・Correction of the saturated vapor pressure for drying in the pre-dryer 46a and the after-dryer 46b according to the paper speed

Further, before the second processing unit 22b of the data processing device 20 calculates the optimum setting value, the actual operation value used for calculating the optimum setting value is corrected using information other than the actual operation value. can be Correction examples of the actual operation value include, for example, those similar to those described above.

1 production system 10 production control system 11 display unit 20 data processor 21 collection unit 22a first processing unit 22b second processing unit 24 output unit 40 paper machine 46a pre-dryer 46b after-dryer B5 seed valve DB actual value database

Claims (9)

a collection unit that collects set values of the final control element that controls the production process of the product at a predetermined cycle, and collects brand information that indicates the brand of the product;
Statistical processing is performed on the set values of the operation terminal collected by the collection unit, and the representative values of the set values of the operation terminal during production of the product of the brand indicated by the brand information are obtained as operational results. a first processing unit that generates a performance value database including the operation performance value obtained as a value and linked with the brand information;
Statistical processing is performed on the operation performance values linked with brand information indicating the next brand to be produced in the production process, among the operation performance values contained in the performance value database, to determine the next brand. a second processing unit that obtains optimum setting values of the final operation end for producing a product;
an output unit that outputs the set value obtained by the second processing unit;
A data processing device comprising: 2. The data processing apparatus according to claim 1, wherein the statistical processing performed by the first processing section is processing for obtaining an average value or a median of the set values of the operating terminals collected by the collecting section. The first processing unit stores, among the set values of the operation terminal collected by the collection unit, the set value obtained when the product of the brand indicated by the brand information is stably produced. 3. The data processing apparatus according to claim 1, wherein said statistical processing is performed. 4. The first processing unit, before performing the statistical processing, performs a process of excluding setting values of the operation terminal collected by the collecting unit that are outside a predetermined range. Data processing apparatus as described. The statistical processing performed by the second processing unit is processing for obtaining an average or median value of the actual operation values linked with brand information indicating the next brand to be produced in the production process, or weighted statistical processing. A data processing apparatus according to any one of claims 1 to 4. The second processing unit, before performing the statistical processing, excludes those out of a predetermined range from the operation performance values linked with the brand information indicating the next brand to be produced in the production process. 6. The data processing apparatus according to any one of claims 1 to 5, which performs processing. a collecting step of collecting setting values of the final control element for controlling the production process of the product at a predetermined cycle and collecting brand information indicating the brand of the product;
Statistical processing is performed on the setting values of the operation terminal collected in the collecting step, and the representative values of the setting values of the operation terminal during production of the product of the brand indicated by the brand information are obtained as operational results. a first processing step of generating a performance value database including the operation performance value obtained as a value and linked with the brand information;
Statistical processing is performed on the operation performance values linked with brand information indicating the next brand to be produced in the production process, among the operation performance values contained in the performance value database, to determine the next brand. a second processing step of determining optimum settings of the final element for producing a product;
an output step of outputting the set value obtained in the second processing step;
A data processing method comprising: a data processing device according to any one of claims 1 to 6;
a production control system for controlling the production of a product by displaying the setting value output from the data processing device as a recommended value on a display unit, or by setting the setting value output from the data processing device to the operation terminal;
production system with The production control system is a system that controls a paper machine that produces paper as the product,
The data processing device collects at least the opening of a seed port valve that supplies pulp raw material to the paper machine and the saturated vapor pressure for drying in the dryer provided in the paper machine as the set values of the operation terminal. ,
The production system according to claim 8.

Images